psariya / text-analytics-of-legal-documents Goto Github PK
View Code? Open in Web Editor NEWUnsupervised clustering techniques to cluster legal-summary documents. In legal cases, the arguments and case points are often constructed referring to past cases. This is a very common task that paralegals carry out today by manually browsing through thousands of reports to find relevant legal case reports so as to cite from them. Our goal is to provide with segmented documents by types of cases so that the paralegals has one less task in their hand. The project includes collating legal summary from 3890 documents, cleaning and preprocessing the text, converting text into vector form to use it with different clustering algorithms and coming up with clustered documents.